{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AVZW4IFFPL2TAFLBTYOGNOXUWZ","short_pith_number":"pith:AVZW4IFF","canonical_record":{"source":{"id":"2505.00503","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T13:14:07Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"2befb230b6ac32c46c5694c3cf98e9d10e3bfe5b95e25c0811948d1826c7b012","abstract_canon_sha256":"e4a3cff7368a1ea1b20fc4735ee87e23af348b5a3f26f5f1868e8cff43f39390"},"schema_version":"1.0"},"canonical_sha256":"05736e20a57af53015619e1c66baf4b67ad5b532550e60c4e225ad931a06ef21","source":{"kind":"arxiv","id":"2505.00503","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00503","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00503v3","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00503","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_12","alias_value":"AVZW4IFFPL2T","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_16","alias_value":"AVZW4IFFPL2TAFLB","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_8","alias_value":"AVZW4IFF","created_at":"2026-07-05T11:33:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AVZW4IFFPL2TAFLBTYOGNOXUWZ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.00503","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T13:14:07Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"2befb230b6ac32c46c5694c3cf98e9d10e3bfe5b95e25c0811948d1826c7b012","abstract_canon_sha256":"e4a3cff7368a1ea1b20fc4735ee87e23af348b5a3f26f5f1868e8cff43f39390"},"schema_version":"1.0"},"canonical_sha256":"05736e20a57af53015619e1c66baf4b67ad5b532550e60c4e225ad931a06ef21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:23.347093Z","signature_b64":"qsALs7+V3+VQxC9RLPSeVB4eYJ76ZV9L1H3WWAk1MEMn0/bNyUsp/Eu+3Z8MI+ROWF9bMUz2TDwk6NfYGoC2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05736e20a57af53015619e1c66baf4b67ad5b532550e60c4e225ad931a06ef21","last_reissued_at":"2026-07-05T11:33:23.346623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:23.346623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.00503","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ahA8MMMZmlxlsHmLcbvTiZ8AfDz1pM+COzm87TTWCIoI2qe/9JJt0FKAzXf+7YYgZnvyEo+2i9juQT4Ys8iDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:43:56.462151Z"},"content_sha256":"e558c3c5798bd03bdcda82d78727264aa5949455cbfed80e0ada404a84ac42eb","schema_version":"1.0","event_id":"sha256:e558c3c5798bd03bdcda82d78727264aa5949455cbfed80e0ada404a84ac42eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AVZW4IFFPL2TAFLBTYOGNOXUWZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational OOD State Correction for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ke Jiang, Wen Jiang, Xiaoyang Tan","submitted_at":"2025-05-01T13:14:07Z","abstract_excerpt":"The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular approach to address this problem. In this paper, we propose a novel method named Density-Aware Safety Perception (DASP) for OOD state correction. Specifically, our method encourages the agent to prioritize actions that lead to outcomes with higher data density, thereby promoting its operation within or the return to in-distribution (safe) regions. To achieve this, we optimize the objective within a variational framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00503","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.00503/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ihKn0WGac/s2zUAlSxu83cNluu+q/zXdaMTCnnuRx/S0ttGpoSXjIB7yoPCKv6YyLE5WWfjSlINATsT2k5YDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:43:56.462929Z"},"content_sha256":"9ac8214c72034f1e56797e283392f7021f80450b53ec3a2a6831951333d9ea68","schema_version":"1.0","event_id":"sha256:9ac8214c72034f1e56797e283392f7021f80450b53ec3a2a6831951333d9ea68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AVZW4IFFPL2TAFLBTYOGNOXUWZ/bundle.json","state_url":"https://pith.science/pith/AVZW4IFFPL2TAFLBTYOGNOXUWZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AVZW4IFFPL2TAFLBTYOGNOXUWZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T18:43:56Z","links":{"resolver":"https://pith.science/pith/AVZW4IFFPL2TAFLBTYOGNOXUWZ","bundle":"https://pith.science/pith/AVZW4IFFPL2TAFLBTYOGNOXUWZ/bundle.json","state":"https://pith.science/pith/AVZW4IFFPL2TAFLBTYOGNOXUWZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AVZW4IFFPL2TAFLBTYOGNOXUWZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AVZW4IFFPL2TAFLBTYOGNOXUWZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e4a3cff7368a1ea1b20fc4735ee87e23af348b5a3f26f5f1868e8cff43f39390","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T13:14:07Z","title_canon_sha256":"2befb230b6ac32c46c5694c3cf98e9d10e3bfe5b95e25c0811948d1826c7b012"},"schema_version":"1.0","source":{"id":"2505.00503","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00503","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00503v3","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00503","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_12","alias_value":"AVZW4IFFPL2T","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_16","alias_value":"AVZW4IFFPL2TAFLB","created_at":"2026-07-05T11:33:23Z"},{"alias_kind":"pith_short_8","alias_value":"AVZW4IFF","created_at":"2026-07-05T11:33:23Z"}],"graph_snapshots":[{"event_id":"sha256:9ac8214c72034f1e56797e283392f7021f80450b53ec3a2a6831951333d9ea68","target":"graph","created_at":"2026-07-05T11:33:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.00503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular approach to address this problem. In this paper, we propose a novel method named Density-Aware Safety Perception (DASP) for OOD state correction. Specifically, our method encourages the agent to prioritize actions that lead to outcomes with higher data density, thereby promoting its operation within or the return to in-distribution (safe) regions. To achieve this, we optimize the objective within a variational framew","authors_text":"Ke Jiang, Wen Jiang, Xiaoyang Tan","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T13:14:07Z","title":"Variational OOD State Correction for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00503","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e558c3c5798bd03bdcda82d78727264aa5949455cbfed80e0ada404a84ac42eb","target":"record","created_at":"2026-07-05T11:33:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e4a3cff7368a1ea1b20fc4735ee87e23af348b5a3f26f5f1868e8cff43f39390","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T13:14:07Z","title_canon_sha256":"2befb230b6ac32c46c5694c3cf98e9d10e3bfe5b95e25c0811948d1826c7b012"},"schema_version":"1.0","source":{"id":"2505.00503","kind":"arxiv","version":3}},"canonical_sha256":"05736e20a57af53015619e1c66baf4b67ad5b532550e60c4e225ad931a06ef21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05736e20a57af53015619e1c66baf4b67ad5b532550e60c4e225ad931a06ef21","first_computed_at":"2026-07-05T11:33:23.346623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:23.346623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qsALs7+V3+VQxC9RLPSeVB4eYJ76ZV9L1H3WWAk1MEMn0/bNyUsp/Eu+3Z8MI+ROWF9bMUz2TDwk6NfYGoC2Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:23.347093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00503","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e558c3c5798bd03bdcda82d78727264aa5949455cbfed80e0ada404a84ac42eb","sha256:9ac8214c72034f1e56797e283392f7021f80450b53ec3a2a6831951333d9ea68"],"state_sha256":"1b51aac3876d35e379cb6f38a7d19b7bc8a6b2d52c187ad11321f975dc1d6e7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14PB5dgM5LX7Z+VxQUdZgFr2RXQh98zcrrcMg4VgUtyKPTgmqxZ+9+V7lMBDLOgKG3g/6tQTuGsLLFU9Z93WAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:43:56.469840Z","bundle_sha256":"5a9fd07cf208c4b3de25cf9a82a54c06bca39fbc0bafcf072413fc60f701a1a2"}}